Roberto Verdone

Francesco Pase, Marco Giordani, Giampaolo Cuozzo et al.

This paper addresses the problem of enabling inter-machine Ultra-Reliable Low-Latency Communication (URLLC) in future 6G Industrial Internet of Things (IIoT) networks. As far as the Radio Access Network (RAN) is concerned, centralized pre-configured resource allocation requires scheduling grants to be disseminated to the User Equipments (UEs) before uplink transmissions, which is not efficient for URLLC, especially in case of flexible/unpredictable traffic. To alleviate this burden, we study a distributed, user-centric scheme based on machine learning in which UEs autonomously select their uplink radio resources without the need to wait for scheduling grants or preconfiguration of connections. Using simulation, we demonstrate that a Multi-Armed Bandit (MAB) approach represents a desirable solution to allocate resources with URLLC in mind in an IIoT environment, in case of both periodic and aperiodic traffic, even considering highly populated networks and aggressive traffic.

Marco Skocaj, Francesca Conserva, Nicol Sarcone Grande et al.

The advent of novel 5G services and applications with binding latency requirements and guaranteed Quality of Service (QoS) hastened the need to incorporate autonomous and proactive decision-making in network management procedures. The objective of our study is to provide a thorough analysis of predictive latency within 5G networks by utilizing real-world network data that is accessible to mobile network operators (MNOs). In particular, (i) we present an analytical formulation of the user-plane latency as a Hypoexponential distribution, which is validated by means of a comparative analysis with empirical measurements, and (ii) we conduct experimental results of probabilistic regression, anomaly detection, and predictive forecasting leveraging on emerging domains in Machine Learning (ML), such as Bayesian Learning (BL) and Machine Learning on Graphs (GML). We test our predictive framework using data gathered from scenarios of vehicular mobility, dense-urban traffic, and social gathering events. Our results provide valuable insights into the efficacy of predictive algorithms in practical applications.

Marco Skocaj, Pedro Enrique Iturria Rivera, Roberto Verdone et al.

Federated Learning (FL) has emerged as a promising framework for distributed training of AI-based services, applications, and network procedures in 6G. One of the major challenges affecting the performance and efficiency of 6G wireless FL systems is the massive scheduling of user devices over resource-constrained channels. In this work, we argue that the uplink scheduling of FL client devices is a problem with a rich relational structure. To address this challenge, we propose a novel, energy-efficient, and importance-aware metric for client scheduling in FL applications by leveraging Unsupervised Graph Representation Learning (UGRL). Our proposed approach introduces a relational inductive bias in the scheduling process and does not require the collection of training feedback information from client devices, unlike state-of-the-art importance-aware mechanisms. We evaluate our proposed solution against baseline scheduling algorithms based on recently proposed metrics in the literature. Results show that, when considering scenarios of nodes exhibiting spatial relations, our approach can achieve an average gain of up to 10% in model accuracy and up to 17 times in energy efficiency compared to state-of-the-art importance-aware policies.

Francesco Pase, Marco Giordani, Sara Cavallero et al.

Industrial Internet of Things (IIoT) networks will provide Ultra-Reliable Low-Latency Communication (URLLC) to support critical processes underlying the production chains. However, standard protocols for allocating wireless resources may not optimize the latency-reliability trade-off, especially for uplink communication. For example, centralized grant-based scheduling can ensure almost zero collisions, but introduces delays in the way resources are requested by the User Equipments (UEs) and granted by the gNB. In turn, distributed scheduling (e.g., based on random access), in which UEs autonomously choose the resources for transmission, may lead to potentially many collisions especially when the traffic increases. In this work we propose DIStributed combinatorial NEural linear Thompson Sampling (DISNETS), a novel scheduling framework that combines the best of the two worlds. By leveraging a feedback signal from the gNB and reinforcement learning, the UEs are trained to autonomously optimize their uplink transmissions by selecting the available resources to minimize the number of collisions, without additional message exchange to/from the gNB. DISNETS is a distributed, multi-agent adaptation of the Neural Linear Thompson Sampling (NLTS) algorithm, which has been further extended to admit multiple parallel actions. We demonstrate the superior performance of DISNETS in addressing URLLC in IIoT scenarios compared to other baselines.

Lorenzo Mario Amorosa, Zhan Gao, Tony Chahoud et al.

Sixth-generation (6G) wireless networks evolve from connecting devices to connecting intelligence. The focus turns to Goal-Oriented Communications, where the effectiveness of communication is assessed through task-level objectives over traditional throughput-centric metrics. As communication intertwines with learning at the edge, distributed inference over wireless networks faces a critical trade-off between task accuracy and efficient radio resource use. Traditional communication schemes (e.g., OFDMA) are not designed for this trade-off, often facing challenges related to scalability and latency. Therefore, we propose a novel goal-oriented framework that integrates over-the-air computation with spatio-temporal graph learning. Leveraging the wireless channel as an analog aggregation layer, the proposed framework enables low-latency message passing while efficiently aggregating semantically relevant features from distributed nodes. Theoretical analysis confirms that our analog architecture converges to the expressive power of digital message passing, while offering decisive scalability advantages. We assess the framework in proactive line-of-sight blockage prediction for millimeter-wave networks. Through high-fidelity ray-tracing simulations, the framework exhibits strong inductive generalization to unseen networks and adapts to domain shifts via lightweight transfer learning, matching or even outperforming digital baselines with significantly reduced communication overhead.

Lorenzo Mario Amorosa, Marco Skocaj, Roberto Verdone et al.

The ever-increasing demand for high-quality and heterogeneous wireless communication services has driven extensive research on dynamic optimization strategies in wireless networks. Among several possible approaches, multi-agent deep reinforcement learning (MADRL) has emerged as a promising method to address a wide range of complex optimization problems like power control. However, the seamless application of MADRL to a variety of network optimization problems faces several challenges related to convergence. In this paper, we present the use of graphs as communication-inducing structures among distributed agents as an effective means to mitigate these challenges. Specifically, we harness graph neural networks (GNNs) as neural architectures for policy parameterization to introduce a relational inductive bias in the collective decision-making process. Most importantly, we focus on modeling the dynamic interactions among sets of neighboring agents through the introduction of innovative methods for defining a graph-induced framework for integrated communication and learning. Finally, the superior generalization capabilities of the proposed methodology to larger networks and to networks with different user categories is verified through simulations.

Theofanis P. Raptis, Weronika Maria Bachan, Roberto Verdone

We investigate cross-layer performance diagnostics for an O-RAN instance by jointly analyzing application-level latency and radio-layer behavior from a real measurement campaign. Measurements were conducted at multiple link distances (2, 6 and 11 meters) using two representative UE configurations (a commercial smartphone and a modem-based device), under both static conditions and a controlled dynamic obstruction scenario. Rather than relying on averages, the study adopts tail-focused latency characterization (e.g., 95th percentile and exceedance probabilities) and connects it to scheduler- and link-adaptation indicators (e.g., block error behavior, modulation/coding selection and signal quality). The results reveal (i) UE-dependent differences that primarily manifest in the latency tail, (ii) systematic scaling of tail latency with distance and payload and (iii) cases where radio-layer dynamics are detectable even when end-to-end latency appears stable, motivating the need for cross-layer evidence. Distinct from much of the existing literature (often centered on throughput, simulated setups, or single-layer KPIs) this work contributes a measurement-driven methodology for interpretable O-RAN diagnostics and proposes lightweight, window-based "degradation flags" that combine tail latency and radio indicators to support practical monitoring and troubleshooting.

Marco Skocaj, Lorenzo Mario Amorosa, Giorgio Ghinamo et al.

Recent years witnessed a remarkable increase in the availability of data and computing resources in communication networks. This contributed to the rise of data-driven over model-driven algorithms for network automation. This paper investigates a Minimization of Drive Tests (MDT)-driven Deep Reinforcement Learning (DRL) algorithm to optimize coverage and capacity by tuning antennas tilts on a cluster of cells from TIM's cellular network. We jointly utilize MDT data, electromagnetic simulations, and network Key Performance indicators (KPIs) to define a simulated network environment for the training of a Deep Q-Network (DQN) agent. Some tweaks have been introduced to the classical DQN formulation to improve the agent's sample efficiency, stability, and performance. In particular, a custom exploration policy is designed to introduce soft constraints at training time. Results show that the proposed algorithm outperforms baseline approaches like DQN and best-fist search in terms of long-term reward and sample efficiency. Our results indicate that MDT-driven approaches constitute a valuable tool for autonomous coverage and capacity optimization of mobile radio networks.